This is an automated email from the ASF dual-hosted git repository. shuke987 pushed a commit to branch codex/report-review-runtime-effort in repository https://gitbox.apache.org/repos/asf/doris-skills.git
commit 32c766e45670a878daa80629d9bdecfb457b7c50 Author: shuke <[email protected]> AuthorDate: Wed Aug 19 17:02:17 2026 +0800 fix: report exact review effort across runtimes --- skills/doris-repo-review/SKILL.md | 12 ++++++++---- skills/doris-repo-review/references/pr-comment-format.md | 2 +- skills/doris-repo-review/scripts/post-pass-comment.sh | 9 +++++++-- 3 files changed, 16 insertions(+), 7 deletions(-) diff --git a/skills/doris-repo-review/SKILL.md b/skills/doris-repo-review/SKILL.md index c460e38..a78e779 100644 --- a/skills/doris-repo-review/SKILL.md +++ b/skills/doris-repo-review/SKILL.md @@ -1,6 +1,6 @@ --- name: doris-repo-review -description: Given a PR URL (`/doris-repo-review https://github.com/apache/doris/pull/66807`), first check whether the current directory's branch and commit match that PR, and if they do not, align the current directory to the PR head without disturbing local work (refuse to switch when tracked files are modified and hand the decision back to the user); then review it with the same pipeline apache/doris CI runs (Code Review Runner) - main-agent risk scan, 1-3 full-review subagents plus r [...] +description: Review an Apache Doris PR from a local clone with the same multi-agent, shared-ledger convergence workflow as the CI Code Review Runner. Use when the user supplies a PR to `/doris-repo-review`, asks to review a Doris PR locally, or asks for the CI-style review flow. Safely align only the current worktree to the exact PR head, refuse to disturb tracked local changes, write equivalent English and Chinese review documents with verified path-line anchors, and never build, test, [...] --- # Local pipeline-style Doris code review @@ -334,7 +334,7 @@ cat > "$CTX/pr-comment-notes.md" <<'EOF' EOF $S/post-pass-comment.sh --ctx "$CTX" \ - --model "<exact model id of this session>" --effort "${CLAUDE_EFFORT:-unknown}" \ + --model "<exact model id of this session>" --effort "<exact effort or unknown>" \ --findings <blocker>,<major>,<minor>,<nit> \ --rounds <r> --converged <true|false> \ --notes-file "$CTX/pr-comment-notes.md" \ @@ -343,8 +343,12 @@ $S/post-pass-comment.sh --ctx "$CTX" \ - **`--model` is the exact model id of the session doing the review** (`claude-opus-5[1m]`, `gpt-5.6-sol`, …), taken from what this session was told about itself - never a guess, never a - bare family name. `--effort` comes from `$CLAUDE_EFFORT`. The comment is a public, signed - statement about who reviewed the code; both fields are what make it auditable. + bare family name. **`--effort` is the exact effort of this session, never a guess.** In Claude + Code, use `$CLAUDE_EFFORT`. In Codex, use the current task's reasoning effort only when the + runtime or task context exposes it explicitly; do not infer it from `~/.codex/config.toml`, + because a task-level override may differ. A launcher may set `DORIS_REVIEW_EFFORT` for this + session. If no authoritative source is available, pass `unknown`. The comment is a public, + auditable statement about who reviewed the code and with which runtime settings. - The dry run runs **every** precondition and prints the exact body. **Show that body to the user and wait for a go**, then re-run the identical command **without `--dry-run`**. Never post without that confirmation. diff --git a/skills/doris-repo-review/references/pr-comment-format.md b/skills/doris-repo-review/references/pr-comment-format.md index a26488e..70d077f 100644 --- a/skills/doris-repo-review/references/pr-comment-format.md +++ b/skills/doris-repo-review/references/pr-comment-format.md @@ -59,7 +59,7 @@ converged: true | `reviewed_at` | ISO-8601, minute precision, with offset | when the comment was rendered | | `reviewer` | GitHub login | `gh api user`, falling back to GraphQL `viewer` and `gh auth status` | | `model` | exact model id | passed with `--model`, e.g. `claude-opus-5[1m]`, `gpt-5.6-sol` | -| `effort` | reasoning effort | `--effort`, default `$CLAUDE_EFFORT` | +| `effort` | reasoning effort | `--effort`; default `$DORIS_REVIEW_EFFORT`, then `$CLAUDE_EFFORT`, else `unknown` | | `findings` | inline map | counts per severity; `blocker` and `major` are always 0 in a PASS | | `rounds` | int | convergence rounds actually run (1-3) | | `converged` | bool | `false` means the 3-round cap was hit with candidates still open | diff --git a/skills/doris-repo-review/scripts/post-pass-comment.sh b/skills/doris-repo-review/scripts/post-pass-comment.sh index fcfd6a0..1b058d9 100755 --- a/skills/doris-repo-review/scripts/post-pass-comment.sh +++ b/skills/doris-repo-review/scripts/post-pass-comment.sh @@ -6,7 +6,8 @@ # # --ctx <dir> review context directory (must contain meta.env) # --model <id> exact model id of the reviewing agent, e.g. claude-opus-5[1m] -# --effort <s> reasoning effort (default: $CLAUDE_EFFORT, else "unknown") +# --effort <s> exact reasoning effort (default: $DORIS_REVIEW_EFFORT, +# then $CLAUDE_EFFORT, else "unknown") # --findings b,m,mi,n blocker,major,minor,nit counts (default 0,0,0,0) # --rounds <n> convergence rounds actually run (default 1) # --converged true|false (default true) @@ -24,7 +25,7 @@ set -euo pipefail CTX="" MODEL="" -EFFORT="${CLAUDE_EFFORT:-unknown}" +EFFORT="${DORIS_REVIEW_EFFORT:-${CLAUDE_EFFORT:-unknown}}" FINDINGS="0,0,0,0" ROUNDS="1" CONVERGED="true" @@ -76,6 +77,10 @@ REPO_ROOT="$(read_meta REPO_ROOT)" [ -n "$PR_URL" ] || PR_URL="https://github.com/${UPSTREAM_REPO}/pull/${PR_NUMBER}"; case "$CONVERGED" in true|false) ;; *) echo "ERROR: --converged takes true or false." >&2; exit 2 ;; esac +case "$EFFORT" in + minimal|low|medium|high|xhigh|max|ultra|unknown) ;; + *) echo "ERROR: --effort must name the exact runtime effort or 'unknown'." >&2; exit 2 ;; +esac [[ "$ROUNDS" =~ ^[0-9]+$ ]] || { echo "ERROR: --rounds takes a number." >&2; exit 2; } IFS=',' read -r F_BLOCKER F_MAJOR F_MINOR F_NIT <<<"$FINDINGS" for v in "$F_BLOCKER" "$F_MAJOR" "$F_MINOR" "$F_NIT"; do --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
